A Question answering System with a sequence to sequence grammatical correction

Abstract

Dialogue or conversational systems including chatbots, and personal assistants are becoming ubiquitous in modern society. Here we present a question answering system that's help a customer to search a product in an ecommerce website and inquiring about it. This article describes a question answering bot, which is based on deep learning. We develop a set of deep learning models for natural language retrieval and generation --- including recurrent neural networks, sequence-to-sequence models and attention mechanism --- and evaluate them in the context of natural language processing. Thus; we have used those technologies in a grammatical correction system, and a question answering system by passing the first model result as input to the second one, in order to improve result.